Java GC 源码分析(1)

Java GC 源码分析(1)

System.gc()入口

hotspot/src/share/vm/memory/universe.cpp：

jint Universe::initialize_heap() {

  if (UseParallelGC) {
#if INCLUDE_ALL_GCS
    Universe::_collectedHeap = new ParallelScavengeHeap();
#else  // INCLUDE_ALL_GCS
    fatal("UseParallelGC not supported in this VM.");
#endif // INCLUDE_ALL_GCS

  } else if (UseG1GC) {
#if INCLUDE_ALL_GCS
    G1CollectorPolicy* g1p = new G1CollectorPolicy();
    g1p->initialize_all();
    G1CollectedHeap* g1h = new G1CollectedHeap(g1p);
    Universe::_collectedHeap = g1h;
#else  // INCLUDE_ALL_GCS
    fatal("UseG1GC not supported in java kernel vm.");
#endif // INCLUDE_ALL_GCS

  } else {
    GenCollectorPolicy *gc_policy;

    if (UseSerialGC) {
      gc_policy = new MarkSweepPolicy();
    } else if (UseConcMarkSweepGC) {
#if INCLUDE_ALL_GCS
      if (UseAdaptiveSizePolicy) {
        gc_policy = new ASConcurrentMarkSweepPolicy();
      } else {
        gc_policy = new ConcurrentMarkSweepPolicy();
      }
#else  // INCLUDE_ALL_GCS
    fatal("UseConcMarkSweepGC not supported in this VM.");
#endif // INCLUDE_ALL_GCS
    } else { // default old generation
      gc_policy = new MarkSweepPolicy();
    }
    gc_policy->initialize_all();

    Universe::_collectedHeap = new GenCollectedHeap(gc_policy);
  }

  jint status = Universe::heap()->initialize();
  if (status != JNI_OK) {
    return status;
  }

• 通用收集堆的初始化

jint GenCollectedHeap::initialize() {
  CollectedHeap::pre_initialize();

  int i;
  _n_gens = gen_policy()->number_of_generations();

  // While there are no constraints in the GC code that HeapWordSize
  // be any particular value, there are multiple other areas in the
  // system which believe this to be true (e.g. oop->object_size in some
  // cases incorrectly returns the size in wordSize units rather than
  // HeapWordSize).
  guarantee(HeapWordSize == wordSize, "HeapWordSize must equal wordSize");

  // The heap must be at least as aligned as generations.
  size_t gen_alignment = Generation::GenGrain;

  _gen_specs = gen_policy()->generations();

  // Make sure the sizes are all aligned.
  for (i = 0; i < _n_gens; i++) {
    _gen_specs[i]->align(gen_alignment);
  }

  // Allocate space for the heap.

  char* heap_address;
  size_t total_reserved = 0;
  int n_covered_regions = 0;
  ReservedSpace heap_rs;

  size_t heap_alignment = collector_policy()->heap_alignment();

  heap_address = allocate(heap_alignment, &total_reserved,
                          &n_covered_regions, &heap_rs);

  if (!heap_rs.is_reserved()) {
    vm_shutdown_during_initialization(
      "Could not reserve enough space for object heap");
    return JNI_ENOMEM;
  }

  _reserved = MemRegion((HeapWord*)heap_rs.base(),
                        (HeapWord*)(heap_rs.base() + heap_rs.size()));

  // It is important to do this in a way such that concurrent readers can't
  // temporarily think somethings in the heap.  (Seen this happen in asserts.)
  _reserved.set_word_size(0);
  _reserved.set_start((HeapWord*)heap_rs.base());
  size_t actual_heap_size = heap_rs.size();
  _reserved.set_end((HeapWord*)(heap_rs.base() + actual_heap_size));

  _rem_set = collector_policy()->create_rem_set(_reserved, n_covered_regions);
  set_barrier_set(rem_set()->bs());

  _gch = this;

  for (i = 0; i < _n_gens; i++) {
    ReservedSpace this_rs = heap_rs.first_part(_gen_specs[i]->max_size(), false, false);
    _gens[i] = _gen_specs[i]->init(this_rs, i, rem_set());
    heap_rs = heap_rs.last_part(_gen_specs[i]->max_size());
  }
  clear_incremental_collection_failed();

#if INCLUDE_ALL_GCS
  // If we are running CMS, create the collector responsible
  // for collecting the CMS generations.
  if (collector_policy()->is_concurrent_mark_sweep_policy()) {
    bool success = create_cms_collector();
    if (!success) return JNI_ENOMEM;
  }
#endif // INCLUDE_ALL_GCS

  return JNI_OK;
}

• 通用收集堆的收集接口

void GenCollectedHeap::collect(GCCause::Cause cause) {
  if (should_do_concurrent_full_gc(cause)) {
#if INCLUDE_ALL_GCS
    // mostly concurrent full collection
    collect_mostly_concurrent(cause);
#else  // INCLUDE_ALL_GCS
    ShouldNotReachHere();
#endif // INCLUDE_ALL_GCS
  } else {
#ifdef ASSERT
    if (cause == GCCause::_scavenge_alot) {
      // minor collection only
      collect(cause, 0);
    } else {
      // Stop-the-world full collection
      collect(cause, n_gens() - 1);
    }
#else
    // Stop-the-world full collection
    collect(cause, n_gens() - 1);
#endif
  }
}

void GenCollectedHeap::collect(GCCause::Cause cause, int max_level) {
  // The caller doesn't have the Heap_lock
  assert(!Heap_lock->owned_by_self(), "this thread should not own the Heap_lock");
  MutexLocker ml(Heap_lock);
  collect_locked(cause, max_level);
}

void GenCollectedHeap::collect_locked(GCCause::Cause cause) {
  // The caller has the Heap_lock
  assert(Heap_lock->owned_by_self(), "this thread should own the Heap_lock");
  collect_locked(cause, n_gens() - 1);
}

// this is the private collection interface
// The Heap_lock is expected to be held on entry.

void GenCollectedHeap::collect_locked(GCCause::Cause cause, int max_level) {
  // Read the GC count while holding the Heap_lock
  unsigned int gc_count_before      = total_collections();
  unsigned int full_gc_count_before = total_full_collections();
  {
    MutexUnlocker mu(Heap_lock);  // give up heap lock, execute gets it back
    VM_GenCollectFull op(gc_count_before, full_gc_count_before,
                         cause, max_level);
    VMThread::execute(&op);
  }
}

其中VM_Operation实现了如下接口方法：

  // Called by VM thread - does in turn invoke doit(). Do not override this
  void evaluate();

  // evaluate() is called by the VMThread and in turn calls doit().
  // If the thread invoking VMThread::execute((VM_Operation*) is a JavaThread,
  // doit_prologue() is called in that thread before transferring control to
  // the VMThread.
  // If doit_prologue() returns true the VM operation will proceed, and
  // doit_epilogue() will be called by the JavaThread once the VM operation
  // completes. If doit_prologue() returns false the VM operation is cancelled.
  virtual void doit()                            = 0;
  virtual bool doit_prologue()                   { return true; };
  virtual void doit_epilogue()                   {}; // Note: Not called if mode is: _concurrent

---

• 通用垃圾收集过程

void VM_GenCollectFull::doit() {
  SvcGCMarker sgcm(SvcGCMarker::FULL);

  GenCollectedHeap* gch = GenCollectedHeap::heap();
  GCCauseSetter gccs(gch, _gc_cause);
  gch->do_full_collection(gch->must_clear_all_soft_refs(), _max_level);
}

收集过程：

void GenCollectedHeap::do_collection(bool  full,
                                     bool   clear_all_soft_refs,
                                     size_t size,
                                     bool   is_tlab,
                                     int    max_level) {
  bool prepared_for_verification = false;
  ResourceMark rm;
  DEBUG_ONLY(Thread* my_thread = Thread::current();)

  assert(SafepointSynchronize::is_at_safepoint(), "should be at safepoint");
  assert(my_thread->is_VM_thread() ||
         my_thread->is_ConcurrentGC_thread(),
         "incorrect thread type capability");
  assert(Heap_lock->is_locked(),
         "the requesting thread should have the Heap_lock");
  guarantee(!is_gc_active(), "collection is not reentrant");
  assert(max_level < n_gens(), "sanity check");

  if (GC_locker::check_active_before_gc()) {
    return; // GC is disabled (e.g. JNI GetXXXCritical operation)
  }

  const bool do_clear_all_soft_refs = clear_all_soft_refs ||
                          collector_policy()->should_clear_all_soft_refs();

  ClearedAllSoftRefs casr(do_clear_all_soft_refs, collector_policy());

  const size_t metadata_prev_used = MetaspaceAux::allocated_used_bytes();

  print_heap_before_gc();

  {
    FlagSetting fl(_is_gc_active, true);

    bool complete = full && (max_level == (n_gens()-1));
    const char* gc_cause_prefix = complete ? "Full GC" : "GC";
    gclog_or_tty->date_stamp(PrintGC && PrintGCDateStamps);
    TraceCPUTime tcpu(PrintGCDetails, true, gclog_or_tty);
    GCTraceTime t(GCCauseString(gc_cause_prefix, gc_cause()), PrintGCDetails, false, NULL);

    gc_prologue(complete);
    increment_total_collections(complete);

    size_t gch_prev_used = used();

    int starting_level = 0;
    if (full) {
      // Search for the oldest generation which will collect all younger
      // generations, and start collection loop there.
      for (int i = max_level; i >= 0; i--) {
        if (_gens[i]->full_collects_younger_generations()) {
          starting_level = i;
          break;
        }
      }
    }

    bool must_restore_marks_for_biased_locking = false;

    int max_level_collected = starting_level;
    for (int i = starting_level; i <= max_level; i++) {
      if (_gens[i]->should_collect(full, size, is_tlab)) {
        if (i == n_gens() - 1) {  // a major collection is to happen
          if (!complete) {
            // The full_collections increment was missed above.
            increment_total_full_collections();
          }
          pre_full_gc_dump(NULL);    // do any pre full gc dumps
        }
        // Timer for individual generations. Last argument is false: no CR
        // FIXME: We should try to start the timing earlier to cover more of the GC pause
        GCTraceTime t1(_gens[i]->short_name(), PrintGCDetails, false, NULL);
        TraceCollectorStats tcs(_gens[i]->counters());
        TraceMemoryManagerStats tmms(_gens[i]->kind(),gc_cause());

        size_t prev_used = _gens[i]->used();
        _gens[i]->stat_record()->invocations++;
        _gens[i]->stat_record()->accumulated_time.start();

        // Must be done anew before each collection because
        // a previous collection will do mangling and will
        // change top of some spaces.
        record_gen_tops_before_GC();

        if (PrintGC && Verbose) {
          gclog_or_tty->print("level=%d invoke=%d size=" SIZE_FORMAT,
                     i,
                     _gens[i]->stat_record()->invocations,
                     size*HeapWordSize);
        }

        if (VerifyBeforeGC && i >= VerifyGCLevel &&
            total_collections() >= VerifyGCStartAt) {
          HandleMark hm;  // Discard invalid handles created during verification
          if (!prepared_for_verification) {
            prepare_for_verify();
            prepared_for_verification = true;
          }
          Universe::verify(" VerifyBeforeGC:");
        }
        COMPILER2_PRESENT(DerivedPointerTable::clear());

        if (!must_restore_marks_for_biased_locking &&
            _gens[i]->performs_in_place_marking()) {
          // We perform this mark word preservation work lazily
          // because it's only at this point that we know whether we
          // absolutely have to do it; we want to avoid doing it for
          // scavenge-only collections where it's unnecessary
          must_restore_marks_for_biased_locking = true;
          BiasedLocking::preserve_marks();
        }

        // Do collection work
        {
          // Note on ref discovery: For what appear to be historical reasons,
          // GCH enables and disabled (by enqueing) refs discovery.
          // In the future this should be moved into the generation's
          // collect method so that ref discovery and enqueueing concerns
          // are local to a generation. The collect method could return
          // an appropriate indication in the case that notification on
          // the ref lock was needed. This will make the treatment of
          // weak refs more uniform (and indeed remove such concerns
          // from GCH). XXX

          HandleMark hm;  // Discard invalid handles created during gc
          save_marks();   // save marks for all gens
          // We want to discover references, but not process them yet.
          // This mode is disabled in process_discovered_references if the
          // generation does some collection work, or in
          // enqueue_discovered_references if the generation returns
          // without doing any work.
          ReferenceProcessor* rp = _gens[i]->ref_processor();
          // If the discovery of ("weak") refs in this generation is
          // atomic wrt other collectors in this configuration, we
          // are guaranteed to have empty discovered ref lists.
          if (rp->discovery_is_atomic()) {
            rp->enable_discovery(true /*verify_disabled*/, true /*verify_no_refs*/);
            rp->setup_policy(do_clear_all_soft_refs);
          } else {
            // collect() below will enable discovery as appropriate
          }
          _gens[i]->collect(full, do_clear_all_soft_refs, size, is_tlab);
          if (!rp->enqueuing_is_done()) {
            rp->enqueue_discovered_references();
          } else {
            rp->set_enqueuing_is_done(false);
          }
          rp->verify_no_references_recorded();
        }
        max_level_collected = i;

        // Determine if allocation request was met.
        if (size > 0) {
          if (!is_tlab || _gens[i]->supports_tlab_allocation()) {
            if (size*HeapWordSize <= _gens[i]->unsafe_max_alloc_nogc()) {
              size = 0;
            }
          }
        }

        COMPILER2_PRESENT(DerivedPointerTable::update_pointers());

        _gens[i]->stat_record()->accumulated_time.stop();

        update_gc_stats(i, full);

        if (VerifyAfterGC && i >= VerifyGCLevel &&
            total_collections() >= VerifyGCStartAt) {
          HandleMark hm;  // Discard invalid handles created during verification
          Universe::verify(" VerifyAfterGC:");
        }

        if (PrintGCDetails) {
          gclog_or_tty->print(":");
          _gens[i]->print_heap_change(prev_used);
        }
      }
    }

    // Update "complete" boolean wrt what actually transpired --
    // for instance, a promotion failure could have led to
    // a whole heap collection.
    complete = complete || (max_level_collected == n_gens() - 1);

    if (complete) { // We did a "major" collection
      // FIXME: See comment at pre_full_gc_dump call
      post_full_gc_dump(NULL);   // do any post full gc dumps
    }

    if (PrintGCDetails) {
      print_heap_change(gch_prev_used);

      // Print metaspace info for full GC with PrintGCDetails flag.
      if (complete) {
        MetaspaceAux::print_metaspace_change(metadata_prev_used);
      }
    }

    for (int j = max_level_collected; j >= 0; j -= 1) {
      // Adjust generation sizes.
      _gens[j]->compute_new_size();
    }

    if (complete) {
      // Delete metaspaces for unloaded class loaders and clean up loader_data graph
      ClassLoaderDataGraph::purge();
      MetaspaceAux::verify_metrics();
      // Resize the metaspace capacity after full collections
      MetaspaceGC::compute_new_size();
      update_full_collections_completed();
    }

    // Track memory usage and detect low memory after GC finishes
    MemoryService::track_memory_usage();

    gc_epilogue(complete);

    if (must_restore_marks_for_biased_locking) {
      BiasedLocking::restore_marks();
    }
  }

  AdaptiveSizePolicy* sp = gen_policy()->size_policy();
  AdaptiveSizePolicyOutput(sp, total_collections());

  print_heap_after_gc();

#ifdef TRACESPINNING
  ParallelTaskTerminator::print_termination_counts();
#endif
}